© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27076
    Prev
    Next
    INDEX
    Explanations

    json objects and class members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arto
    -0.08
    ulk
    -0.07
    ivo
    -0.07
    .house
    -0.07
    elog
    -0.07
    arrant
    -0.07
    __.
    -0.06
    ardan
    -0.06
    vre
    -0.06
     forKey
    -0.06
    POSITIVE LOGITS
    ä¸Ĭåı£
    0.08
    øb
    0.07
    нием
    0.07
    aissez
    0.07
    çį¨
    0.07
    >>()
    0.06
    zens
    0.06
    oux
    0.06
    definitions
    0.06
    Ùijا
    0.06
    Activations Density 0.166%

    No Known Activations